update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- super_glue
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: 1_6e-3_1_0.1
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# 1_6e-3_1_0.1
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the super_glue dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.9552
|
22 |
+
- Accuracy: 0.7294
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.006
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 11
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 100.0
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
53 |
+
| 1.1794 | 1.0 | 590 | 0.8903 | 0.6217 |
|
54 |
+
| 1.096 | 2.0 | 1180 | 0.6682 | 0.5771 |
|
55 |
+
| 0.8877 | 3.0 | 1770 | 1.0585 | 0.3792 |
|
56 |
+
| 0.8825 | 4.0 | 2360 | 0.6340 | 0.6229 |
|
57 |
+
| 0.891 | 5.0 | 2950 | 0.8424 | 0.6217 |
|
58 |
+
| 0.7749 | 6.0 | 3540 | 0.6586 | 0.5752 |
|
59 |
+
| 0.8351 | 7.0 | 4130 | 0.6083 | 0.6373 |
|
60 |
+
| 0.7693 | 8.0 | 4720 | 0.6969 | 0.5813 |
|
61 |
+
| 0.869 | 9.0 | 5310 | 0.5918 | 0.6777 |
|
62 |
+
| 0.7739 | 10.0 | 5900 | 0.6373 | 0.6416 |
|
63 |
+
| 0.741 | 11.0 | 6490 | 0.7306 | 0.6306 |
|
64 |
+
| 0.6366 | 12.0 | 7080 | 0.6535 | 0.6951 |
|
65 |
+
| 0.6503 | 13.0 | 7670 | 0.5655 | 0.7021 |
|
66 |
+
| 0.7297 | 14.0 | 8260 | 0.8470 | 0.5847 |
|
67 |
+
| 0.5637 | 15.0 | 8850 | 0.6914 | 0.6278 |
|
68 |
+
| 0.6233 | 16.0 | 9440 | 0.7041 | 0.6862 |
|
69 |
+
| 0.5812 | 17.0 | 10030 | 0.6282 | 0.7049 |
|
70 |
+
| 0.5423 | 18.0 | 10620 | 1.1433 | 0.5612 |
|
71 |
+
| 0.5366 | 19.0 | 11210 | 0.6643 | 0.7168 |
|
72 |
+
| 0.5369 | 20.0 | 11800 | 0.9787 | 0.6832 |
|
73 |
+
| 0.4828 | 21.0 | 12390 | 0.8036 | 0.7049 |
|
74 |
+
| 0.5085 | 22.0 | 12980 | 0.8132 | 0.6425 |
|
75 |
+
| 0.4488 | 23.0 | 13570 | 0.7755 | 0.6651 |
|
76 |
+
| 0.4184 | 24.0 | 14160 | 0.6817 | 0.7104 |
|
77 |
+
| 0.448 | 25.0 | 14750 | 0.6490 | 0.7193 |
|
78 |
+
| 0.4123 | 26.0 | 15340 | 0.7854 | 0.6728 |
|
79 |
+
| 0.4196 | 27.0 | 15930 | 0.7012 | 0.7138 |
|
80 |
+
| 0.4119 | 28.0 | 16520 | 0.7525 | 0.7116 |
|
81 |
+
| 0.3811 | 29.0 | 17110 | 0.7333 | 0.7012 |
|
82 |
+
| 0.3698 | 30.0 | 17700 | 1.1169 | 0.6480 |
|
83 |
+
| 0.3382 | 31.0 | 18290 | 0.6635 | 0.7232 |
|
84 |
+
| 0.338 | 32.0 | 18880 | 0.7444 | 0.7266 |
|
85 |
+
| 0.3359 | 33.0 | 19470 | 1.0398 | 0.6621 |
|
86 |
+
| 0.3071 | 34.0 | 20060 | 0.8387 | 0.7291 |
|
87 |
+
| 0.3001 | 35.0 | 20650 | 0.7648 | 0.7281 |
|
88 |
+
| 0.3221 | 36.0 | 21240 | 0.7485 | 0.7266 |
|
89 |
+
| 0.2973 | 37.0 | 21830 | 0.7841 | 0.7260 |
|
90 |
+
| 0.2801 | 38.0 | 22420 | 0.8797 | 0.7242 |
|
91 |
+
| 0.2666 | 39.0 | 23010 | 0.9504 | 0.7028 |
|
92 |
+
| 0.2575 | 40.0 | 23600 | 0.8444 | 0.7217 |
|
93 |
+
| 0.2796 | 41.0 | 24190 | 1.1635 | 0.7067 |
|
94 |
+
| 0.2596 | 42.0 | 24780 | 0.8979 | 0.7217 |
|
95 |
+
| 0.2465 | 43.0 | 25370 | 0.8439 | 0.7177 |
|
96 |
+
| 0.2475 | 44.0 | 25960 | 0.9628 | 0.7028 |
|
97 |
+
| 0.2394 | 45.0 | 26550 | 0.9549 | 0.7156 |
|
98 |
+
| 0.2192 | 46.0 | 27140 | 0.8422 | 0.7251 |
|
99 |
+
| 0.2253 | 47.0 | 27730 | 0.9386 | 0.7245 |
|
100 |
+
| 0.2063 | 48.0 | 28320 | 0.9686 | 0.7028 |
|
101 |
+
| 0.2258 | 49.0 | 28910 | 0.8843 | 0.7165 |
|
102 |
+
| 0.2114 | 50.0 | 29500 | 0.9566 | 0.7324 |
|
103 |
+
| 0.2039 | 51.0 | 30090 | 1.0167 | 0.7073 |
|
104 |
+
| 0.182 | 52.0 | 30680 | 0.9182 | 0.7303 |
|
105 |
+
| 0.1825 | 53.0 | 31270 | 0.9879 | 0.7147 |
|
106 |
+
| 0.1827 | 54.0 | 31860 | 0.9542 | 0.7199 |
|
107 |
+
| 0.1727 | 55.0 | 32450 | 0.9540 | 0.7245 |
|
108 |
+
| 0.1857 | 56.0 | 33040 | 0.9222 | 0.7294 |
|
109 |
+
| 0.182 | 57.0 | 33630 | 1.1263 | 0.7021 |
|
110 |
+
| 0.1716 | 58.0 | 34220 | 0.9947 | 0.7239 |
|
111 |
+
| 0.1659 | 59.0 | 34810 | 0.9969 | 0.7220 |
|
112 |
+
| 0.1596 | 60.0 | 35400 | 0.9764 | 0.7193 |
|
113 |
+
| 0.1656 | 61.0 | 35990 | 1.0089 | 0.7281 |
|
114 |
+
| 0.1545 | 62.0 | 36580 | 0.9712 | 0.7193 |
|
115 |
+
| 0.1429 | 63.0 | 37170 | 0.9785 | 0.7245 |
|
116 |
+
| 0.1567 | 64.0 | 37760 | 1.0706 | 0.7076 |
|
117 |
+
| 0.1493 | 65.0 | 38350 | 0.9546 | 0.7287 |
|
118 |
+
| 0.1453 | 66.0 | 38940 | 0.9959 | 0.7245 |
|
119 |
+
| 0.1384 | 67.0 | 39530 | 0.9687 | 0.7300 |
|
120 |
+
| 0.1409 | 68.0 | 40120 | 0.9739 | 0.7202 |
|
121 |
+
| 0.1388 | 69.0 | 40710 | 1.1173 | 0.7232 |
|
122 |
+
| 0.1366 | 70.0 | 41300 | 0.9598 | 0.7254 |
|
123 |
+
| 0.1429 | 71.0 | 41890 | 1.0048 | 0.7070 |
|
124 |
+
| 0.1384 | 72.0 | 42480 | 0.9816 | 0.7205 |
|
125 |
+
| 0.1221 | 73.0 | 43070 | 1.0827 | 0.7232 |
|
126 |
+
| 0.131 | 74.0 | 43660 | 1.0217 | 0.7294 |
|
127 |
+
| 0.1282 | 75.0 | 44250 | 0.9694 | 0.7287 |
|
128 |
+
| 0.1308 | 76.0 | 44840 | 1.0198 | 0.7208 |
|
129 |
+
| 0.1252 | 77.0 | 45430 | 1.0261 | 0.7278 |
|
130 |
+
| 0.1252 | 78.0 | 46020 | 0.9709 | 0.7272 |
|
131 |
+
| 0.117 | 79.0 | 46610 | 1.0140 | 0.7257 |
|
132 |
+
| 0.1171 | 80.0 | 47200 | 1.0226 | 0.7321 |
|
133 |
+
| 0.1132 | 81.0 | 47790 | 1.0880 | 0.7199 |
|
134 |
+
| 0.116 | 82.0 | 48380 | 0.9087 | 0.7254 |
|
135 |
+
| 0.1156 | 83.0 | 48970 | 0.9973 | 0.7257 |
|
136 |
+
| 0.103 | 84.0 | 49560 | 1.0078 | 0.7287 |
|
137 |
+
| 0.1096 | 85.0 | 50150 | 1.0122 | 0.7263 |
|
138 |
+
| 0.1097 | 86.0 | 50740 | 1.0316 | 0.7312 |
|
139 |
+
| 0.098 | 87.0 | 51330 | 1.0030 | 0.7275 |
|
140 |
+
| 0.1035 | 88.0 | 51920 | 0.9551 | 0.7214 |
|
141 |
+
| 0.0978 | 89.0 | 52510 | 1.0217 | 0.7287 |
|
142 |
+
| 0.1001 | 90.0 | 53100 | 0.9817 | 0.7291 |
|
143 |
+
| 0.1011 | 91.0 | 53690 | 0.9693 | 0.7281 |
|
144 |
+
| 0.0957 | 92.0 | 54280 | 1.0017 | 0.7199 |
|
145 |
+
| 0.0946 | 93.0 | 54870 | 0.9992 | 0.7278 |
|
146 |
+
| 0.0976 | 94.0 | 55460 | 0.9660 | 0.7291 |
|
147 |
+
| 0.0961 | 95.0 | 56050 | 0.9572 | 0.7278 |
|
148 |
+
| 0.0944 | 96.0 | 56640 | 0.9801 | 0.7269 |
|
149 |
+
| 0.0944 | 97.0 | 57230 | 0.9527 | 0.7272 |
|
150 |
+
| 0.0936 | 98.0 | 57820 | 0.9543 | 0.7266 |
|
151 |
+
| 0.0939 | 99.0 | 58410 | 0.9540 | 0.7281 |
|
152 |
+
| 0.0915 | 100.0 | 59000 | 0.9552 | 0.7294 |
|
153 |
+
|
154 |
+
|
155 |
+
### Framework versions
|
156 |
+
|
157 |
+
- Transformers 4.30.0
|
158 |
+
- Pytorch 2.0.1+cu117
|
159 |
+
- Datasets 2.14.4
|
160 |
+
- Tokenizers 0.13.3
|